SkillTrust — AI Skills Selection Assistant

Pre-install score

68 · Manual review

One primary score for ranking and pre-install decisions; Evidence completeness 67%.

Risk decision

Documented signals

network_access, requires_token, shell_execution

Install readiness

source-documented · source-link only

SkillTrust only shows install guidance and copy actions; it never executes installs.

Before you install

Review source, permissions, and execution risk first, then alternatives. Scores prioritize review; they do not replace manual judgment.

Install guidance

Install and compatible tools

This area handles the execution step: review explicit or inferred tool fit, then decide whether to copy commands.

Review source first

Explicitly supported

Candidate support (inferred)

Candidate tools are inferred signals, not official compatibility certifications.

Claude

Shown with the common install pattern for this tool.

No explicit install command yet. Review the repository and install docs before deciding.

Copy is disabled because no explicit command is available yet.

Before you install

Review source and permissions first. If no explicit command is available, start from the repository guidance.

Current risk hints: network_access, requires_token, shell_execution

Audit main stage

Start with the overall gaps before deciding to continue

This stage turns 15 audit dimensions into one pre-install score; the constellation only explains the gaps instead of becoming a second score.

C

68/ 100Install advice：Check before install

The purpose is visible, but source, permissions, or install evidence needs checking.

Current advice

Review before install

Review source, permissions, and execution details before copying commands.

Execution profile

High

Check command, file-write, and network behavior first.

Evidence completeness

67%

This shows how much public evidence supports the score; it is not a safety certification.

SkillTrust risk constellation

Use one constellation to see the 15-dimension weak spots

Start with the overall shape and the weakest three items, then use the list below for full labels, scores, and actions.

Constellation focusPermission scope & least privilege33High risk

15-dim mapShape firstRead the gaps

Start here

Read the weakest three first, then move into the full 15-item list.

Top 3 gaps

Full 15-dimension list

Select any item to see how it supports the pre-install score

The default view starts from the lowest scores; switch to risk-first when you want severity before score.

Source and author

Repository

Agnuxo1/Token-compression-system-for-improving-agent-cognition

Author

Agnuxo1

Community signal

0 stars · 0 forks

Favorites

0

Last updated

2026-04-16

Primary source

Agnuxo1/Token-compression-system-for-improving-agent-cognition

Source status

Clear source

Install method

source-documented

Task scenario

Engineering & Ops

Strong alternatives

Candidates in Engineering & Ops that are most worth comparing first

Compare

Agent Sync

Repository: openclaw/skills

Author: SingggggYee · Source status: Clear source

Score 84Clear source

Manual review

One config, everywhere.

Score basis：Clear source · High execution risk · Claude · Evidence completeness 67%

Agnuxo1 Token Compression System For Improving Agent Cognition

Install and compatible tools

Start with the overall gaps before deciding to continue

Use one constellation to see the 15-dimension weak spots

Select any item to see how it supports the pre-install score

Agent Sync

Claude Code Agent Monitor

Convert documentation, GitHub repos, PDFs, codebases, videos, and more into structured AI skills using the skill-seekers CLI. Use this skill whenever the user wants to create an AI

Posthog

More from this author

Github Agnuxo1 P2pclaw Mcp Server

Enigmagent Mcp

N8n Nodes Enigmagent

EnigmAgent

Install and compatible tools

Start with the overall gaps before deciding to continue

Use one constellation to see the 15-dimension weak spots

Select any item to see how it supports the pre-install score

Agent Sync

Can SkillTrust install this for me?

Does a high score mean it is definitely safe?

How are alternatives selected?

Claude Code Agent Monitor

Convert documentation, GitHub repos, PDFs, codebases, videos, and more into structured AI skills using the skill-seekers CLI. Use this skill whenever the user wants to create an AI

Posthog

More from this author

Github Agnuxo1 P2pclaw Mcp Server

Enigmagent Mcp

N8n Nodes Enigmagent

EnigmAgent